spacewalk01 / depth-anything-tensorrt

Unofficial cpp and python implementation of depth-anything model using tensorrt api.

https://depth-anything.github.io/

spacewalk01/depth-anything-tensorrt Issues

Engine generated is for Relative Depth or Metric Depth?
Updated a month ago2
Can't reach higher fps
Updated a month ago
If I use the python version, will it be slower than the c++ version?
Closed 2 months ago3
About on Jetson orin
Closed 2 months ago13
Unable to create engine from onnx model
Closed 2 months ago40
Made a comfyui custom node
Closed 2 months ago
on my NVIDIA-RTX3090 gpu, time of per frame is 35ms±, is this speed normal?
Closed 3 months ago9
Depth-Anything TensorRT Python
Closed 4 months ago4
Fail to create engine file with metric_depth_vits model
Closed 3 months ago5
How to export the large model?
Closed 3 months ago1
How to export onnx with dynamic shape?
Closed 3 months ago2
export works for vitb, but not for vitl
Closed 3 months ago9
BUG
Closed 3 months ago1
Uncaught exception detected: Unable to open library: nvinfer_plugin.dll
Closed 3 months ago6
depth-anaything-tensorrt-simplified.exe - System Error
Closed 3 months ago3
cannot export to onnx
Closed 4 months ago1
Missing requirements in python branch
Closed 4 months ago
Installation Guide
Closed 4 months ago12
[E] Error[4]: If_1249_OutputLayer: IIfConditionalOutputLayer inputs must have the same shape.
Closed 4 months ago5
Cuda Runtime (an illegal memory access was encountered)
Closed 4 months ago2
a tip for small memory computer failed run export_to_onnx.py when encoder = 'vitl'
Closed 4 months ago1
Is linux supported now？
Closed 4 months ago2
Fail to create engine
Closed 4 months ago4
Jetson support
Closed 4 months ago1